A Unified Decision Framework for Phase I Dose-Finding Designs

TL;DR

This paper introduces a unified decision framework for phase I dose-finding designs, revealing their common elements and differences, and providing insights to guide practitioners in selecting suitable methods.

Contribution

It presents a simple, unified framework that encompasses various existing dose-finding designs, clarifying their shared structure and theoretical foundations.

Findings

Shared likelihood functions and loss functions among designs

Differences mainly in prior distribution choices

Theoretical links to popular designs like mTPI, BOIN, and CRM

Abstract

The purpose of a phase I dose-finding clinical trial is to investigate the toxicity profiles of various doses for a new drug and identify the maximum tolerated dose. Over the past three decades, various dose-finding designs have been proposed and discussed, including conventional model-based designs, new model-based designs using toxicity probability intervals, and rule-based designs. We present a simple decision framework that can generate several popular designs as special cases. We show that these designs share common elements under the framework, such as the same likelihood function, the use of loss functions, and the nature of the optimal decisions as Bayes rules. They differ mostly in the choice of the prior distributions. We present theoretical results on the decision framework and its link to specific and popular designs like mTPI, BOIN, and CRM. These results provide useful insights into the designs and their underlying assumptions, and convey information to help practitioners select an appropriate design.